Improving Text-Based Person Retrieval by Excavating All-Round Information Beyond Color.

Text-based person retrieval is the process of searching a massive visual resource library for images of a particular pedestrian, based on a textual query. Existing approaches often suffer from a problem of color (CLR) over-reliance, which can result in a suboptimal person retrieval performance by distracting the model from other important visual cues such as texture and structure information. To handle this problem, we propose a novel framework to Excavate All-round Information Beyond Color for the task of text-based person retrieval, which is therefore termed EAIBC.

Synchronous Spatiotemporal Graph Transformer: A New Framework for Traffic Data Prediction.

Modeling the spatiotemporal relationship (STR) of traffic data is important yet challenging for existing graph networks. These methods usually capture features separately in temporal and spatial dimensions or represent the spatiotemporal data by adopting multiple local spatial-temporal graphs. The first kind of method mentioned above is difficult to capture potential temporal-spatial relationships, while the other is limited for long-term feature extraction due to its local receptive field.

End-to-End Deep One-Class Learning for Anomaly Detection in UAV Video Stream.

In recent years, the use of drones for surveillance tasks has been on the rise worldwide. However, in the context of anomaly detection, only normal events are available for the learning process. Therefore, the implementation of a generative learning method in an unsupervised mode to solve this problem becomes fundamental.

RecapNet: Action Proposal Generation Mimicking Human Cognitive Process.

Generating action proposals in untrimmed videos is a challenging task, since video sequences usually contain lots of irrelevant contents and the duration of an action instance is arbitrary. The quality of action proposals is key to action detection performance. The previous methods mainly rely on sliding windows or anchor boxes to cover all ground-truth actions, but this is infeasible and computationally inefficient.

Detection of abnormal events via optical flow feature analysis.

In this paper, a novel algorithm is proposed to detect abnormal events in video streams. The algorithm is based on the histogram of the optical flow orientation descriptor and the classification method. The details of the histogram of the optical flow orientation descriptor are illustrated for describing movement information of the global video frame or foreground frame.

Constrained state estimation for individual localization in wireless body sensor networks.

Wireless body sensor networks based on ultra-wideband radio have recently received much research attention due to its wide applications in health-care, security, sports and entertainment. Accurate localization is a fundamental problem to realize the development of effective location-aware applications above. In this paper the problem of constrained state estimation for individual localization in wireless body sensor networks is addressed.

Object tracking using adaptive covariance descriptor and clustering-based model updating for visual surveillance.

We propose a novel approach for tracking an arbitrary object in video sequences for visual surveillance. The first contribution of this work is an automatic feature extraction method that is able to extract compact discriminative features from a feature pool before computing the region covariance descriptor. As the feature extraction method is adaptive to a specific object of interest, we refer to the region covariance descriptor computed using the extracted features as the adaptive covariance descriptor.

Online least squares one-class support vector machines-based abnormal visual event detection.

The abnormal event detection problem is an important subject in real-time video surveillance. In this paper, we propose a novel online one-class classification algorithm, online least squares one-class support vector machine (online LS-OC-SVM), combined with its sparsified version (sparse online LS-OC-SVM). LS-OC-SVM extracts a hyperplane as an optimal description of training objects in a regularized least squares sense.

Bayesian space-frequency separation of wide-band sound sources by a hierarchical approach.

This paper proposes an efficient solution to the separation of uncorrelated wide-band sound sources which overlap each other in both space and frequency domains. The space-frequency separation is solved in a hierarchical way by (1) expanding the sound sources onto a set of spatial basis functions whose coefficients become the unknowns of the problem (backpropagation step) and (2) blindly demixing the coefficients of the spatial basis into uncorrelated components relating to sources of distinct physical origins (separation step). The backpropagation and separation steps are both investigated from a Bayesian perspective.

Classification of elderly as fallers and non-fallers using Centre of Pressure velocity.

Falls are a leading cause of death in the elderly. One of the most common methods of predicting falls is to evaluate balance using force plate measurement of the Centre of Pressure (COP) displacement. This signal, known as a stabilogram, can be decomposed into movement in anteroposterior (AP) and mediolateral (ML) directions.

Nonlinear chaotic component extraction for postural stability analysis.

This paper proposes a nonlinear analysis of the human postural steadiness system. The analyzed signal is the displacement of the centre of pressure (COP) collected from a force plate used for measuring postural sway. Instead of analyzing the classical nonlinear parameters on the whole signal, the proposed method consists of analyzing the nonlinear dynamics of the intrinsic mode functions (IMF) of the COP signal.

Number of sources uncertainty in blind source separation. Application to EMG signal processing.

This contribution deals with the number of components uncertainty in blind source separation. The number of components is estimated by maximizing its marginal a posteriori probability which favors the simplest explanation of the observed data. Marginalizing (integrating over all the parameters) is implemented through the Laplace approximation based on an efficient wavelet spectral matching separating algorithm.

Hilbert-Huang transformation: application to postural stability analysis.

The aim objective of this paper is the analysis of the Centre Of Pressure (COP) time series by the means of the Hilbert Huang Transformation (HHT). The HHT consists of extracting the Intrinsic Mode Functions (IMFs) from an Empirical Mode Decomposition (EMD), and then applying the Hilbert Transformation on the IMFs. The trace of the HHT in the complex plane has a circular form, with each IMF having its own rotation frequency.

Reconstructed phase spaces of intrinsic mode functions. Application to postural stability analysis.

In this contribution, we propose an efficient nonlinear analysis method characterizing postural steadiness. The analyzed signal is the displacement of the centre of pressure (COP) collected from a force plate used for measuring postural sway. The proposed method consists of analyzing the nonlinear dynamics of the intrinsic mode functions (IMF) of the COP signal.